Computer Rating System Prediction Results for College Football (NCAA IA)

2010 Season Totals

Through
Rank System Pct. Correct Against Spread Absolute Error Bias Mean Square Error games suw sul atsw atsl
1Tom Benson0.738100.4936713.5186-7.3957283.7968462223940
2Fort Heresy Model0.747470.5207313.34280.0253289.087396296100201185
3Linear Regression0.721930.5597813.13730.2985275.692374270104206162
4Bihl System0.718500.5054313.32580.8312276.692373268105186182
5BG Sports0.716580.5224713.33031.6273280.379374268106186170
6Anderson/Hester *0.676470.4823814.06650.2924308.021374253121178191
7Least Squares w/ HFA0.676470.5094915.7607-0.0259389.982374253121188181
8Wolfe *0.673800.4782614.51000.5497320.024374252122176192
9Massey *0.671120.4823814.44570.3929317.676374251123178191
10Martien Maas0.671120.5231617.01040.5056431.875374251123192175
11Logistic Regression0.663100.4986416.8715-2.7261432.490374248126184185
12Thompson SPRS20.713650.4675913.44280.4083286.027447319128202230
13DP Dwiggins0.727090.4755113.4067-3.2487273.865502365137233257
14Thompson SPRS0.691280.4689714.15170.0852318.567447309138204231
15Brent Craig 20.715910.5019913.96770.5210309.305528378150252250
16Austin Sports0.708650.4980813.48560.6090282.490532377155260262
17Covers.com0.726630.4816813.7490-0.9326294.563567412155263283
18Bassett Model0.727720.4857613.42481.2084280.244606441165290307
19Dokter Entropy0.760450.4600012.82530.4164257.753718546172322378
20Computer Adjusted Line0.758380.4857112.41060.2877244.423716543173119126
21Dunkel Index0.754870.4943012.84830.2184264.611718542176347355
22Line (updated)0.7534812.42200.4150245.100718541177
23Massey Ratings0.750700.4921812.9918-0.1753268.537718539179346357
24ARGH Power Ratings0.728920.4703913.20970.4590269.397664484180286322
25System Average0.745130.4757812.7673-0.0624255.497718535183334368
26System Median0.743730.4871112.7773-0.0695255.672718534184340358
27Sagarin Predictive0.743730.4950213.07690.0010268.635718534184348355
28Hank Trexler0.742660.5073715.2392-0.0252391.754715531184344334
29NationalSportsRankings0.742340.5014312.8706-0.1577260.193718533185351349
30Tempo Free Gridiron0.742340.4682413.7897-1.5919301.483718533185317360
31Catherwood Ratings0.741980.5335312.82570.6416262.301717532185358313
32Edward Kambour0.740950.4921813.26900.0757277.326718532186346357
33Line (opening)0.740220.5051212.56150.1187252.069716530186296290
34Laz Index0.739550.4800613.0877-0.5947265.044718531187337365
35Stephen Kerns0.736770.5049913.0266-0.1901262.428718529189354347
36CPA Rankings0.736770.5085513.00660.0177265.661718529189357345
37TW Rankings0.713420.5086614.0236-1.5578311.868663473190323312
38Stat Fox0.735380.5098312.83151.0100261.767718528190337324
39Massey Consensus0.733980.4751113.19400.2370270.907718527191334369
40Atomic Football0.732590.4950212.78600.2589259.991718526192348355
41Ashby AccuRatings0.732590.4778113.0794-0.2296269.735718526192323353
42Brent Craig0.732220.5162213.4310-0.2510282.981717525192350328
43Billingsley+0.731200.4529913.23970.0029274.557718525193318384
44Sportrends0.726630.4924713.3421-0.4214287.264706513193327337
45Howell0.731200.4868013.3057-0.4463278.049718525193332350
46Pigskin Index0.729810.4902512.8398-0.2962258.710718524194327340
47Schmidt Comp. Ratings0.729810.4344713.5202-0.4301282.492718524194305397
48Regression-Based Analys0.728410.4896113.46941.2187285.937718523195330344
49Sagarin0.728410.4651513.28740.0761276.496718523195327376
50Lee Burdorf0.728410.4657113.2511-0.1600277.597718523195326374
51CF By the Numbers0.726120.5044813.11800.6489269.098712517195338332
52Moore Power Ratings0.727020.5000012.9458-0.2447266.675718522196351351
53Born Power Index0.727020.5064013.0030-0.1690264.115718522196356347
54NutShell Sports0.725630.4992913.3127-0.2543277.145718521197351352
55NutShell Combo0.725630.4629613.3721-0.3890276.511718521197325377
56Keeper0.725630.5064013.65161.2470289.373718521197356347
57Beck Elo0.724230.4409713.5768-0.1487284.647718520198310393
58PerformanZ Ratings0.721450.5042713.61040.0840291.185718518200354348
59Dave Congrove0.721060.4957313.1921-0.3063275.925717517200348354
60Payne Power Ratings0.721060.4821713.3321-0.3759280.833717517200338363
61Super List0.720060.4957314.08160.5471304.666718517201348354
62Billingsley0.718660.4950213.6055-0.1945289.522718516202348355
63Laffaye XWP0.716880.4906513.8715-0.9781305.159717514203341354
64Marsee0.714480.4595013.84121.5125296.373718513205312367
65Warren Claassen0.706130.4985813.6229-0.4837290.384718507211350352
66CPA Retro0.699160.4936014.17850.0339313.086718502216347356
67Sagarin Elo0.694990.4679914.08830.1753305.243718499219329374
68Nutshell Girl0.688020.4509214.4449-0.7402327.943718494224317386

* This system does not make predictions.  I make predictions for this
  system by translating it to a new scale that allows for making predictions.



Retrodictive records are found by taking the ratings from the current week
and applying them to the entire season to date.

The ideal system would be one that has the highest correct game decisions,
has the smallest mean error(deviation from the actual game result), and has
a bias of zero.

Mean Error = average[abs(prediction-actual)]

      Bias = agerage(prediction - actual)

      Std. = Standard Deviation of individual game biases